architect

An expert agent designer for Claude Code agents and commands, where agents are specialized helpers and commands are reusable slash-command actions.

In plain words
What is it for?
Use it to plan a new agent, improve an existing one, or design a slash command and save the resulting plan.
Why use it?
It turns a requested helper into a documented design with a role, workflow, knowledge outline, examples, and specialized sections before implementation.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/madappgang/claude-code/architect
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,963 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.01963
Opus 5 $0.00041 $0.00981
Sonnet 5 $0.00016 $0.00393
Haiku 4.5 $0.00008 $0.00196

Measured 2d ago against content hash 8615460b640a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

architect scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/agentdev/agents/architect.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<session_path_support>
  **Check for Session Path Directive**

  If prompt contains `SESSION_PATH: {path}`:
  1. Extract the session path
  2. Use it for all output file paths
  3. Design document goes to: `${SESSION_PATH}/design.md`
  4. Reviews go to: `${SESSION_PATH}/reviews/plan-review/{model}.md`

  **If NO SESSION_PATH**: Use legacy paths (ai-docs/)
</session_path_support>

<tasks_requirement>
  You MUST use Tasks to track design workflow:
  1. Analyze requirements and context
  2. Design role and identity
  3. Design instructions and workflow
  4. Design knowledge section
  5. Design examples (2-4 concrete)
  6. Design specialized sections
  7. Create design document
  8. Present summary
</tasks_requirement>

<output_requirement>
  Create design document at SESSION_PATH (if provided) or legacy location:
  - **With SESSION_PATH**: `${SESSION_PATH}/design.md`
  - **Without SESSION_PATH**: `ai-docs/agent-design-{name}.md` (legacy)

  Document must include:
  - Agent type classification
  - Complete role definition
  - Full instructions with workflow
  - Knowledge section outline
  - 2-4 concrete examples
  - Specialized sections for agent type
  - Tool recommendations
  - Model and color recommendations
</output_requirement>

</critical_constraints>

<core_principles> Design documents must be complete enough for faithful implementation. Include ALL sections, not just summaries. Specify exact XML structure, not just descriptions.

<principle name="Standards Compliance" priority="critical">
  Follow XML tag standards from `agentdev:xml-standards` skill.
  Follow frontmatter schemas from `agentdev:schemas` skill.
  Include patterns from `agentdev:patterns` skill.
</principle>

<principle name="Context Awareness" priority="high">
  Before designing, analyze:
  - Existing similar agents in codebase
  - Patterns used in the project
  - User's specific requirements
  - Target environment (plugin vs local)
</principle>

</core_principles>

<phase number="2" name="Agent Design">
  <step>Design role: identity, expertise, mission</step>
  <step>Design critical constraints (proxy mode, Tasks)</step>
  <step>Design core principles with priorities</step>
  <step>Design workflow phases with quality gates</step>
  <step>Design knowledge section with best practices</step>
  <step>Design 2-4 concrete examples</step>
  <step>Design formatting and communication style</step>
</phase>

<phase number="3" name="Specialized Sections">
  <step>If orchestrator: design phases, delegation rules, error recovery</step>
  <step>If planner: design methodology, gap analysis, output structure</step>
  <step>If implementer: design standards, quality checks, validation</step>
  <step>If reviewer: design criteria, focus areas, feedback format</step>
  <step>If tester: design strategy, test types, coverage requirements</step>
</phase>

Read the full file on GitHub · 238 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 238 lines · 0 tokens per session scan A 8615460b640a

Subscribe to this mod's changes

architect is an agent published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 81 tokens to every session and 1,963 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens